Despite various controversies around its ownership, its moderation policies, its growth efforts. Despite these concerns, TikTok is working very hard to show that it has nothing to hide, that it's a transparent company, that users can trust. It's added a new Transparency Center in LA, where people can stop by and see how it actions its policies, it's limited user data access in order to mitigate potential misuse, and it recently appointed a US-based CEO, adding further separation from its Chinese parent company.
And this week, TikTok has tried to provide another level of transparency, in explaining exactly how its recommendations algorithm works, and how videos gain traction, or don't, on its platform.
As explained by TikTok:
"When you open TikTok and land in your For You feed, you're presented with a stream of videos curated to your interests, making it easy to find content and creators you love. This feed is powered by a recommendation system that delivers content to each user that is likely to be of interest to that particular user."
TikTok outlines the specifics of that recommendation system here, but in essence, these are the key factors.
The main drivers that define which videos appear in each users' feed are:
User interactions - TikTok factors in the videos you like and/or share, the accounts you follow, the comments you post, and the content you create. So, for example, if you post clips using a certain hashtag, there's a higher chance you'll see content with the same tag in your stream.
Video information - This could include details like captions, specific sounds and songs, and again hashtags.
Device and account settings - Lesser influencing factors are things like your language preference, your country setting and your mobile device type. TikTok says that these factors are considered in order to deliver optimal presentation, but they don't get given the same weight as the previous two.
So, TikTok's algorithm is similar to those in operation on most other social platforms - it factors in the content you engage with, then tries to show you more of the same. You would think that commenting would add more weight, and have you seeing more content from that account, while engaging with certain hashtag trends will likely see you presented with more examples.
No great insight there, that's as you would expect. But TikTok does share some other pointers of note for your strategic calculations.
"A strong indicator of interest, such as whether a user finishes watching a longer video from beginning to end, would receive greater weight than a weak indicator, such as whether the video's viewer and creator are both in the same country."
So people watching your videos through to completion will increase your potential to see higher reach.
"To help kick things off we invite new users to select categories of interest, like pets or travel, to help tailor recommendations to their preferences. This allows the app to develop an initial feed, and it will start to polish recommendations based on your interactions with an early set of videos."
Just as with other platforms, TikTok will try to match new users with relevant content, based on interests.
"Your For You feed isn't only shaped by your engagement through the feed itself. When you decide to follow new accounts, for example, that action will help refine your recommendations too, as will exploring hashtags, sounds, effects, and trending topics on the Discover tab."
Again, this is probably obvious, but all user actions are taken into account. If you search for something, that'll factor into your recommendations. So if your brother gets a hold of your phone and looks for crazy videos, you might see flow-on feed impacts.
"Diversity is essential to maintaining a thriving global community, and it brings the many corners of TikTok closer together. To that end, sometimes you may come across a video in your feed that doesn't appear to be relevant to your expressed interests or have amassed a huge number of likes. This is an important and intentional component of our approach to recommendation: bringing a diversity of videos into your For You feed gives you additional opportunities to stumble upon new content categories, discover new creators, and experience new perspectives and ideas as you scroll through your feed."
This may be a less helpful note, but an interesting one either way. TikTok will essentially showcase selected videos, despite their engagement or creator status levels, in order to diversify the feed. How significant an element this is is difficult to say, but it's likely not a major consideration.
But this one may be the most important tidbit from TikTok's algorithm overview:
"While a video is likely to receive more views if posted by an account that has more followers, by virtue of that account having built up a larger follower base, neither follower count nor whether the account has had previous high-performing videos are direct factors in the recommendation system."
That is different to other platforms. Essentially, TikTok's saying that past performance, and profile status, are not considered in its algorithm at all. High profile users will inevitably get more reach, because more people are following them, but TikTok uses individual video stats and engagement to showcase content.
Essentially, TikTok will aim to show you more of the content you like, based on your activity, with each individual post assessed independently, aligned with your noted interests.
TikTok doesn't provide specifics on exactly how much each of these elements is weighted, but the pointers here do explain a lot about why you see what you do in your TikTok feed.
For marketers, that may help to provide more understanding of how to maximize your TikTok videos:
Each video counts independently
Aligning with trending interests will help you connect with more users
Having viewers watch your clips to completion may help
There are no exact science pointers here, but these are the key considerations, based on these insights, that will help you maximize your TikTok performance.
You can read TikTok's full recommendations algorithm overview here.